Report
Self Similarity Matrix based CNN Filter Pruning
| العنوان: | Self Similarity Matrix based CNN Filter Pruning |
|---|---|
| المؤلفون: | Rakshith, S, Vachhani, Jayesh Rajkumar, Gothe, Sourabh Vasant, Khurana, Rishabh |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | In recent years, most of the deep learning solutions are targeted to be deployed in mobile devices. This makes the need for development of lightweight models all the more imminent. Another solution is to optimize and prune regular deep learning models. In this paper, we tackle the problem of CNN model pruning with the help of Self-Similarity Matrix (SSM) computed from the 2D CNN filters. We propose two novel algorithms to rank and prune redundant filters which contribute similar activation maps to the output. One of the key features of our method is that there is no need of finetuning after training the model. Both the training and pruning process is completed simultaneously. We benchmark our method on two of the most popular CNN models - ResNet and VGG and record their performance on the CIFAR-10 dataset. Comment: Paper accepted in the 7th International Conference on Computer Vision & Image Processing (2022) |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2211.01814 |
| رقم الانضمام: | edsarx.2211.01814 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |